agent-bom ingest
Validate and import cloud inventory JSON, generate local scan results
Install & Use
Copy this prompt and send it to your AI assistant (Claude / Cursor / TRAE / Codex / WorkBuddy etc.) to auto-install:
Help me install this AI Skill: agent-bom ingest. It is used for: Validate and import cloud inventory JSON, generate local scan results Full Skill content: https://321skill.com/skills/agent-bom-ingest/raw/index.md Read that page and install it.
The prompt includes a link to the full Skill content. You can also view the full content.
This Skill addresses the challenge of asset inventory in multi-cloud enterprise environments. When operations personnel export inventory JSON from platforms like AWS, Azure, or GCP via scripts or a CMDB, using agent-bom's pull mode directly requires providing cloud credentials, posing security risks and lacking offline capability. This Skill allows users to input pre-exported, standardized JSON files to perform local validation and scanning without any cloud access permissions.
Usage is straightforward: simply prepare your inventory JSON file and instruct the AI via natural language, e.g., "Validate and import inventory.json." It first validates the data format using the built-in inventory.schema.json, ensuring field completeness and correct data types. Upon successful validation, it automatically performs local scanning, generates a dependency graph, conducts policy checks, and supports exporting results in formats like JSON, SARIF, HTML, and Markdown. You can also opt to push results to your self-hosted dashboard by providing the URL and an API Token.
It is ideal for operations and security teams requiring regular cloud asset audits and compliance checks. Enterprises that already export inventory periodically via existing CMDBs or cloud provider APIs can seamlessly integrate this workflow to transform offline data into auditable discovery reports. For AI Agent developers, this is also a valuable tool, enabling AI assistants to analyze infrastructure security without exposing cloud credentials.
It is recommended to use this tool for validation and scanning after each asset change to ensure findings are synchronized with the latest inventory. Note: This Skill requires Python 3.11+ and agent-bom 0.84.4+, and the inventory JSON must comply with the packaged schema specification. If the input file format is incorrect, it will report an error and halt processing to ensure data integrity.
Key Features
Unlike agent-bom's built-in operator-pull mode, this Skill does not require configuring any cloud platform credentials. It runs locally using only the provided pre-generated JSON file, eliminating credential exposure risks and supporting asset scanning in offline environments.
Limitations
Requires Python 3.11+ and agent-bom 0.84.4+. The inventory JSON must strictly adhere to the definitions in `inventory.schema.json`; otherwise, validation will fail. Pushing results to a dashboard is optional and requires the user to provide a URL and API Token.
FAQ
Are cloud platform access keys required?
No. This Skill only processes the JSON file you provide and does not connect directly to any cloud platform, so no access keys are needed.
Which cloud vendor inventory formats are supported?
Supports standardized JSON exports from AWS, Azure, GCP, Snowflake, CMDB, and endpoint collectors, as long as they conform to `inventory.schema.json`.
Installation guide for AI assistants
If your AI coding assistant (Claude Code, Cursor, TRAE etc.) can see this page, send it this message to auto-install:
Visit https://321skill.com/skills/agent-bom-ingest/raw/index.md to read the original Skill definition (Markdown format) for agent-bom ingest, and install it according to the instructions.
Raw Markdown URL for AI: /skills/agent-bom-ingest/raw/index.md